agentleFS
joaoajmatosjoaoajmatos/ze/.claude/skills/doc-style/SKILL.md

doc-style

Skill2 starsChanged 47 days agoUnlicenseView on GitHub

Copyediting rules for Ze's public-facing documentation (root READMEs, VISION.md, CONTRIBUTING.md, SECURITY.md, and docs/*.md). Apply George Orwell's six rules and an ASD-STE100-inspired plain-English discipline whenever drafting or editing these files. Does not apply to specs/, CLAUDE.md, or AGENTS.md.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 13 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this whenever drafting, editing, or reviewing prose in: README.md, VISION.md, CONTRIBUTING.md, SECURITY.md, apps/README.md, …

    line 12
  2. Distinctive:

    Never use a metaphor, simile, or other figure of speech which you are used to seeing in print.

    line 22
  3. Distinctive:

    Never use a long word where a short one will do.

    line 24
  4. Distinctive:

    If it is possible to cut a word out, always cut it out.

    line 25
  5. Distinctive:

    Never use the passive where you can use the active.

    line 26
  6. Distinctive:

    Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.

    line 27
  7. Distinctive:

    Use a specific technical term when accuracy requires it.

    line 40
  8. Distinctive:

    Keep noun groups short; use prepositions to show relationships.

    line 42
  9. Distinctive:

    Write procedures as direct instructions: condition, action, expected result.

    line 43
  10. Distinctive:

    Prefer positive instructions — state what the reader must do.

    line 45
  11. Distinctive:

    Never touch code blocks, commands, file paths, identifiers, package names, table structure, or YAML/JSON snippets — simplify only the prose …

    line 47
  12. Distinctive:

    Read the file before editing.

    line 53
  13. Distinctive:

    Look for: passive constructions, stock metaphors, needless words, jargon with a plain equivalent, inconsistent terminology, bloated noun …

    line 54
  14. Distinctive:

    Do not add or remove documented behavior.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ze Documentation Style

Use this whenever drafting, editing, or reviewing prose in: README.md, VISION.md, CONTRIBUTING.md, SECURITY.md, apps/README.md, core/README.md, integrations/README.md, packages/README.md, plugins/README.md, and any file under docs/.

Out of scope: specs/ (design specs follow spec-kit conventions, not this style), CLAUDE.md, AGENTS.md (agent instructions, not reader-facing prose).

Orwell's six rules

  1. Never use a metaphor, simile, or other figure of speech which you are used to seeing in print.
  2. Never use a long word where a short one will do.
  3. If it is possible to cut a word out, always cut it out.
  4. Never use the passive where you can use the active.
  5. Never use a foreign phrase, a scientific word, or a jargon word if you can think of an everyday English equivalent.
  6. Break any of these rules sooner than say anything outright barbarous.

ASD-STE100 baseline (plain technical English)

  1. Short sentences. One main action or statement per sentence.
  2. Clear subject, active verb. Name the actor when it matters (e.g. "Ze writes the fact," not "the fact is written").
  3. Same term for the same thing — do not vary vocabulary just to avoid repetition.
  4. Familiar words with one precise meaning. Avoid idioms, slang, figurative language, and vague verbs ("leverage," "utilize," "facilitate").
  5. Use a specific technical term when accuracy requires it. Real technical content (LangGraph, asyncpg, WebSocket, Pydantic, …) is not fluff — keep it.
  6. Keep noun groups short; use prepositions to show relationships.
  7. Write procedures as direct instructions: condition, action, expected result.
  8. Prefer positive instructions — state what the reader must do.
  9. Consistent American English spelling.
  10. Never touch code blocks, commands, file paths, identifiers, package names, table structure, or YAML/JSON snippets — simplify only the prose around them.

Workflow

  1. Read the file before editing.
  2. Look for: passive constructions, stock metaphors, needless words, jargon with a plain equivalent, inconsistent terminology, bloated noun phrases, British spellings (British → American: -ise → -ize, -our → -or, etc., except inside code/config where the source string is authoritative).
  3. Make targeted, surgical edits — not a full rewrite. Preserve every technical fact, heading structure, table, code fence, and link exactly. Do not add or remove documented behavior; do not invent content.
  4. docs/package-readme-template.md is a template — keep its placeholder tokens intact and edit only the instructional prose around them.
  5. VISION.md uses deliberate extended metaphor (spine/organ/mind) as its core rhetorical voice — that is not an incidental cliché under rule 1; leave it unless asked to rewrite the document's voice itself.

For large sweeps across many files, split the file list into balanced batches (by line count) and run them as parallel subagents, each briefed with this ruleset in full — fresh agents have no memory of this skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.